李冠彬

所属研究所、院系: 
大数据与计算智能研究所
职称: 
副研究员
E-mail: 
liguanbin@mail.sysu.edu.cn
办公地点: 
中山大学东校区南基础实验楼D302
个人主页: http://guanbinli.com
教师简介: 

李冠彬,博士,副研究员。分别于2009年和2012年在中山大学获学士和硕士学位,2016年在香港大学计算机科学系获博士学位,博士期间获得香港政府奖学金(HKPFS)资助。目前主要从事计算机视觉和机器学习等方面的研究,尤其在视觉显著性检测以及图像视频语义理解等方面取得一系列重要的研究成果,形成较为完整的研究体系。迄今为止,已经累计发表论文40余篇,其中CCF A类/中科院一区论文22篇,包括TPAMI, TNNLS, TIP, TCYB, CVPR,ICCV,AAAI,IJCAI,ACM MM 等。目前担任CCF YOSCEF广州常务委员,CCF计算机视觉专委会委员,CSIG视觉大数据专委会委员,多次受邀在各大学术论坛及企业做学术报告,相关工作被同行学者多次引用和评价,Google Scholar引用超过1000次。在图像视频显著物体检测方面,曾连续四年以第一作者身份在计算机视觉顶级会议CVPR上发表论文四篇,在该研究领域形成一定的影响力。目前主持国家自然科学基金、CCF-腾讯犀牛鸟科研基金、商汤青年科研基金、中山大学青年教师培育等多项科研项目。担任TPAMI、TIP、TNNLS、TCYB、TOG等权威期刊的审稿人,CVPR、IJCAI、AAAI等国际会议程序委员会委员,VISAPP2019领域主席。

研究领域: 
  • 计算机视觉
    • 图像视频智能分析:显著性检测、多标签分类、语义分割、图像视频语句生成、视觉问答等。
    • 底层计算机视觉:图像增强(超分辨重建、图像修复等)、图像风格化
    • 其它应用:视觉跟踪、行人再识别、人群密度估计、交通流量预测
  • 机器学习
    • 深度学习:Deep CNN、LSTM、Attention Modeling, Generative Adversarial Network, Reinforcement Learning ...
    • 传统方法:SVM、Random Forest、Boosting、Metric Learning ...
教育背景: 

2005/09-2009/07:中山大学,计算机科学与技术,学士学位

2009/09-2012/07:中山大学,计算机软件与理论,硕士学位

2012/09-2016/07:香港大学,计算机科学,博士学位

工作经历: 

2016/07-2016/10:香港大学,助理研究员

2016/10-至今:中山大学数据科学与计算机学院,副研究员

海外经历: 

2012/09-2016/07:香港大学,计算机科学,博士学位

科研项目: 

1)2017年国家自然科学基金-青年科学基金(No. 61702565) (主持,30万)

2)2017年CCF-腾讯犀牛鸟科研基金(主持,12万)

3)2018年高校基本科研业务费项目(青年教师培育项目)(主持,15万)

4)2018年商汤青年科研基金项目 (主持,20万)

5)NSFC-广东省人民政府大数据科学研究中心项目 (子课题中大方负责人)

6)广东省科技发展专项资金(前沿与关键技术创新方向-重大科技专项)(参与)

7)2016年国家重点研发计划项目“面向大范围场景透彻感知的视觉大数据智能分析关键技术与验证系统” (参与)

主要学术兼职: 

1. VISAPP2019 领域主席

2.程序委员会委员:CVPR2018, CVPR2019, IJCAI2018, IJCAI2019, AAAI 2019, CVM2017 and ACCV2016.

3.审稿人

  • IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI)
  • IEEE Transactions on Neural Networks and Learning Systems (TNNLS)
  • IEEE Transactions on Image Processing (TIP)
  • IEEE Transactions on Multimedia (TMM)
  • IEEE Transactions on Cybernetics (TCYB)
  • ACM SIGGRAPH2017,SIGGRAPH Asia 2018
代表性论著: 

(*)表示通讯作者

  1. [1] Guanbin Li, Xiang He, Wei Zhang, Huiyou Chang, Le Dong, Liang Lin, "Non-locally Enhanced Encoder-Decoder Network for Single Image De-raining" ACM International Conference on Multimedia(ACM MM), 2018. [CCF A]
  2. [2] Guanbin Li, Yukang Gan, Hejun Wu, Nong Xiao, Liang Lin, "Cross-Modal Attentional Context Learning for RGB-D Object Detection" IEEE Transactions on Image Processing(T-IP), 2018. [CCF A]
  3. [3] Guanbin Li and Yizhou Yu, "Contrast-Oriented Deep Neural Networks for Salient Object Detection" IEEE Transactions on Neural Networks and Learning Systems(T-NNLS), 2018. [中科院一区]
  4. [4] Guanbin Li, Yuan Xie, Tianhao Wei, Keze Wang, Liang Lin, "Flow Guided Recurrent Neural Encoder for Video Salient Object Detection" IEEE Conference on Computer Vision and Pattern Recognition(CVPR), 2018. [CCF A]
  5. [5] Guanbin Li, Xin Zhu, Yirui Zeng, Qing Wang, Liang Lin, "Semantic Relationships Guided Representation Learning for Facial Action Unit Recognition" Association for the Advancement of Artificial Intelligence(AAAI), 2019. [CCF A]
  6. [6] Guanbin Li, Yuan Xie, Liang Lin, "Weakly Supervised Salient Object Detection Using Image Labels" Association for the Advancement of Artificial Intelligence(AAAI), 2018. [CCF A]
  7. [7] Guanbin Li, Yuan Xie, Liang Lin and Yizhou Yu, "Instance-Level Salient Object Segmentation" IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2017. [CCF A]
  8. [8] Guanbin Li and Yizhou Yu, "Deep Contrast Learning for Salient Object Detection" IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2016. [CCF A]
  9. [9] Guanbin Li and Yizhou Yu, "Visual Saliency Detection Based on Multiscale Deep CNN Features" IEEE Transactions on Image Processing(T-IP), 2016. [CCF A]
  10. [10] Guanbin Li and Yizhou Yu, "Visual Saliency Based on Multiscale Deep Features" IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2015. [CCF A]
  11. [11] Sibei Yang, Guanbin Li*, Yizhou Yu, "Cross-Modal Relationship Inference for Grounding Referring Expressions" IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2019. [CCF A]
  12. [12] Chao Chen, Guanbin Li*, Ruijia Xu, Tianshui Chen, Meng Wang, Liang Lin, “CluterNet: Deep Hierarchical Cluster Network with Rigorously Rotation-Invariant Representation for Point Cloud Analysis”, IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2019. [CCF A]
  13. [13] Yukai Shi, Guanbin Li*, Qingxing Cao, Keze Wang, Liang Lin, "Face Hallucination by Attentive Sequence Optimization with Reinforcement Learning", IEEE Transactions on Pattern Analysis and Machine Intelligence (T-PAMI), [CCF A] [中科院一区]
  14. [14] Xu Cai, Yang Wu, Guanbin Li*, Ziliang Chen, Liang Lin, "FRAME Revisited: An Interpretation View Based on Particle Evolution" Association for the Advancement of Artificial Intelligence(AAAI), 2019. [CCF A]
  15. [15] Haofeng Li, Guanbin Li*, Liang Lin, Yizhou Yu, "Context-Aware Semantic Inpainting" IEEE Transactions on Cybernetics(T-Cybernetics), 2018. [中科院一区]
  16. [16] Haofeng Li, Guanbin Li*, Yizhou Yu, "ROSA: Robust Salient Object Detection against Adversarial Attacks" IEEE Transactions on Cybernetics(T-Cybernetics), 2018. [中科院一区]
  17. [17] Xian Wu, Guanbin Li*, Qingxing Cao, Qingge Ji, Liang Lin, "Interpretable Video Captioning via Trajectory Structured Localization" IEEE Conference on Computer Vision and Pattern Recognition(CVPR), 2018. [CCF A]
  18. [18] Xiang He, Sibei Yang, Guanbin Li*, Haofeng Li, Huiyou Chang, Yizhou Yu, "Non-Local Context Encoder: Robust Biomedical Image Segmentation against Adversarial Attacks", Association for the Advancement of Artificial Intelligence(AAAI), 2019. [CCF A]
  19. [19] Lingbo Liu, Ruimao Zhang, Jiefeng Peng, Guanbin Li*, Bowen Du, Liang Lin, "Attentive LSTM Crowd Flow Machines" ACM International Conference on Multimedia(ACM MM), 2018. [CCF A]
  20. [20] Lingbo Liu, Hongjun Wang, Guanbin Li*, Wanli Ouyang, Liang Lin, "Crowd Counting using Deep Recurrent Spatial-Aware Network" International Joint Conference on Artificial Intelligence(IJCAI), 2018. [CCF A]
  21. [21] Tianshui Chen, Zhouxia Wang, Guanbin Li*, Liang Lin "Recurrent Attention Reinforcement Learning for Multi-label Image Recognition" Association for the Advancement of Artificial Intelligence(AAAI), 2018. [CCF A]
  22. [22] Qingxing Cao, Xiaodan Liang, Bailin Li, Guanbin Li, Liang Lin, "Visual Question Reasoning on General Dependency Tree" IEEE Conference on Computer Vision and Pattern Recognition(CVPR), 2018. [CCF A]
  23. [23] Lingbo Liu, Guanbin Li, Yuan Xie, Yizhou Yu, Liang Lin, "Facial Landmark Localization in the Wild by Backbone-Branches Representation Learning." Fourth IEEE International Conference on Multimedia Big Data (BigMM). 2018.
  24. [24] Lili Huang, Jiefeng Peng, Ruimao Zhang, Guanbin Li, Liang Lin, "Learning deep representations for semantic image parsing: a comprehensive overview", Frontiers of Computer Science, 2018.
  25. [25] Zhouxia Wang, Tianshui Chen, Guanbin Li, Ruijia Xu and Liang Lin, "Multi-label Image Recognition by Recurrently Discovering Attentional Regions" International Conference on Computer Vision (ICCV), 2017. [CCF A]
  26. [26] Qingxing Cao, Liang Lin, Yukai Shi, Xiaodan Liang, Guanbin Li, "Attention Aware Face Hallucination via Deep Reinforcement Learning" IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2017. [CCF A]
  27. [27] Wei Zhang, Chaowei Fang, Guanbin Li*, "Automatic colorization with improved spatial coherence and boundary localization" Journal of Computer Science and Technology (JCST), 2017. [CCF B]
  28. [28] Guanbin Li, Sai Bi, Jue Wang, Yingqing Xu, and Yizhou Yu, "A Drawing Assistant for Generating Color Sketches from Photos" IEEE Computer Graphics and Applications (CG&A), 2016.